Staff AI Engineer

Staff AI/ML Engineer (RAG & Agent Systems)

San Mateo, CA (Hybrid)

Our client is a Series B startup with over $100M raised building an AI-driven analytics platform.

This is a high-impact, hands-on role focused on designing and scaling production-grade AI systems, specifically around agent architectures, retrieval systems, and AI-powered data transformation.

Role Overview

You’ll take ownership of building end-to-end AI agents that operate over complex datasets in production environments. This includes everything from problem decomposition and retrieval design to evaluation frameworks and system optimization.

Key areas of focus include:

• Architecting multi-step AI agents (reasoning, retrieval, tool use, error handling, output validation)
• Owning RAG pipelines, including vector-based and graph-based retrieval (Neo4j)
• Designing knowledge representations that enable accurate reasoning over schemas, lineage, and semantics
• Building AI systems that generate production-grade code and data transformations from natural language
• Driving evaluation, iteration, and quality improvements across AI systems
• Scaling systems in production with attention to latency, throughput, and observability

You’ll work closely with data and platform teams and integrate with modern data ecosystems like Databricks, Snowflake, BigQuery, Spark, and DuckDB.

Core Requirements

• Experience building and deploying AI systems (ideally coding agents or similar) into production
• Strong hands-on engineering mindset; comfortable iterating quickly and rebuilding when needed
• Proven experience supporting production systems (not just experimentation or research environments)
• Strong Python skills
• Experience with RAG systems, vector databases, and retrieval pipelines
• Familiarity with knowledge graphs (e.g., Neo4j)
• Experience with AWS and Kubernetes

Nice to Have

• Experience with Scala or Go (Java is also relevant)
• Background in data infrastructure, analytics platforms, or large-scale data processing